Sentiment Analysis in Indian Elections: Unraveling Public Perception of the Karnataka Elections With Transformers

Abstract

This study explores the utility of sentiment classification in political decision-making through an analysis of Twitter sentiment surrounding the 2023 Karnataka elections. Utilizing transformer-based models for sentiment analysis in Indic languages, the research employs innovative data collection methodologies, including novel data augmentation techniques. The primary focus is on sentiment classification, discerning positive, negative, and neutral posts, particularly regarding the defeat of the Bharatiya JanataParty (BJP) or the victory of the Indian National Congress (INC). Leveraging high-performing transformer architectures like IndicBERT, coupled with precise hyper parameter tuning, the AI models used in this study exhibit exceptional predictive accuracy, notably predicting the INC's electoral success. These findings underscore the potential of state-of-the-art transformer-based models in capturing and understanding sentiment dynamics within Indian politics. Implications are far-reaching, providing invaluable insights for political stakeholders preparing for the 2024 Lok Sabha elections. This study stands as a testament to the potential of sentiment analysis as a pivotal tool in political decision-making, specifically in non-Western nations.